Citation URL Validity Analysis on DRBench
5.4Non-resolving Rategemini-2.5-flash-search
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| gemini-2.5-flash-searchProvider=Google, URLs=2,4332026.04 | 5.4 | 4.6 | 0.8 | |
| gpt-4.1Provider=OpenAI, URLs=3362026.04 | 5.4 | 5.4 | 0 | |
| gemini-2.5-pro-searchProvider=Google, URLs=1,6092026.04 | 5.9 | 4.8 | 1.1 | |
| gpt-4.1-miniProvider=OpenAI, URLs=2962026.04 | 7.4 | 7.4 | 0 | |
| claude-3-5-sonnet-searchProvider=Anthropic, URLs=6412026.04 | 7.8 | 3 | 4.8 | |
| claude-3-7-sonnet-searchProvider=Anthropic, URLs=1,7352026.04 | 8.5 | 3.2 | 5.2 | |
| gpt-4o-mini-search-prev.Provider=OpenAI, URLs=4022026.04 | 8.7 | 8.7 | 0 | |
| gpt-4o-search-previewProvider=OpenAI, URLs=3872026.04 | 8.8 | 8.8 | 0 | |
| openai-deepresearchProvider=OpenAI, URLs=4,1212026.04 | 10.1 | 3.5 | 6.6 | |
| gemini-2.5-pro-deepres.Provider=Google, URLs=11,3092026.04 | 18.5 | 13.3 | 5.2 |